checkpoint-99/trainer_state.json

{
  "best_metric": 0.30745795369148254,
  "best_model_checkpoint": "asd_pronunciation_w2v_xlsr-reg/checkpoint-99",
  "epoch": 8.977777777777778,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.98,
      "eval_loss": 0.8269791603088379,
      "eval_mse": 0.8274638056755066,
      "eval_runtime": 67.3404,
      "eval_samples_per_second": 31.497,
      "eval_steps_per_second": 0.995,
      "step": 11
    },
    {
      "epoch": 1.98,
      "eval_loss": 0.4631172716617584,
      "eval_mse": 0.46300947666168213,
      "eval_runtime": 67.2163,
      "eval_samples_per_second": 31.555,
      "eval_steps_per_second": 0.997,
      "step": 22
    },
    {
      "epoch": 2.98,
      "eval_loss": 0.351409912109375,
      "eval_mse": 0.3515050709247589,
      "eval_runtime": 67.5563,
      "eval_samples_per_second": 31.396,
      "eval_steps_per_second": 0.992,
      "step": 33
    },
    {
      "epoch": 3.98,
      "eval_loss": 0.3585782051086426,
      "eval_mse": 0.35852691531181335,
      "eval_runtime": 69.7976,
      "eval_samples_per_second": 30.388,
      "eval_steps_per_second": 0.96,
      "step": 44
    },
    {
      "epoch": 4.98,
      "eval_loss": 0.4412296712398529,
      "eval_mse": 0.4412075877189636,
      "eval_runtime": 79.1138,
      "eval_samples_per_second": 26.809,
      "eval_steps_per_second": 0.847,
      "step": 55
    },
    {
      "epoch": 5.98,
      "eval_loss": 0.430486798286438,
      "eval_mse": 0.43049314618110657,
      "eval_runtime": 72.5547,
      "eval_samples_per_second": 29.233,
      "eval_steps_per_second": 0.923,
      "step": 66
    },
    {
      "epoch": 6.98,
      "eval_loss": 0.42916765809059143,
      "eval_mse": 0.4291659891605377,
      "eval_runtime": 95.5528,
      "eval_samples_per_second": 22.197,
      "eval_steps_per_second": 0.701,
      "step": 77
    },
    {
      "epoch": 7.98,
      "eval_loss": 0.4343053996562958,
      "eval_mse": 0.43428245186805725,
      "eval_runtime": 66.5007,
      "eval_samples_per_second": 31.894,
      "eval_steps_per_second": 1.008,
      "step": 88
    },
    {
      "epoch": 8.98,
      "eval_loss": 0.30745795369148254,
      "eval_mse": 0.3074318766593933,
      "eval_runtime": 66.2359,
      "eval_samples_per_second": 32.022,
      "eval_steps_per_second": 1.012,
      "step": 99
    }
  ],
  "max_steps": 550,
  "num_train_epochs": 50,
  "total_flos": 2.8846380565942047e+19,
  "trial_name": null,
  "trial_params": null
}